def extract(file_path):
'''
a single task a worker would perform
return a tuple(whehter the parsing is successful, whether there is now document has been added)
'''
extractor = ExtractorFactory.get_extractor(file_path)
extension = os.path.splitext(file_path)[-1]
if extractor is not None and extension in ['.txt'
]: # only parse the txt file
print 'Parsing', file_path
# if extractor.is_parsed():
# print 'This file has been parse '
# return False
try:
if extractor.parse_document():
inc = extractor.update(ignore_parsed=True)
return True, inc
else:
logging.error('Failed to parse %s, continue' % (file_path, ))
return False, 0
except DuplicateKeyError:
logging.error('document existed, continue...')
return False, 0
else:
return False, 0
def extract(file_path):
'''
a single task a worker would perform
return a tuple(whehter the parsing is successful, whether there is now document has been added)
'''
extractor = ExtractorFactory.get_extractor(file_path)
extension = os.path.splitext(file_path)[-1]
if extractor is not None and extension in ['.txt']: # only parse the txt file
print 'Parsing', file_path
# if extractor.is_parsed():
# print 'This file has been parse '
# return False
try:
if extractor.parse_document():
inc = extractor.update(ignore_parsed=True)
return True, inc
else:
logging.error('Failed to parse %s, continue' % (file_path,))
return False, 0
except DuplicateKeyError:
logging.error('document existed, continue...')
return False, 0
else:
return False, 0
def run(self):
while True:
# get the file_path from the Q
if not self.queue.empty():
file_path = self.queue.get()
extension = os.path.splitext(file_path)[-1]
# get the extractor from unique factory
extractor_lock.acquire()
extractor = ExtractorFactory.get_extractor(file_path)
extractor_lock.release()
if extractor is not None and extension in [
'.txt'
]: # only parse the txt file
print 'worker', os.getpid(), 'is parsing', file_path
try:
if extractor.parse_document():
extractor.insert()
else:
print 'parser error for %s, continue' % (
file_path, )
except DuplicateKeyError:
print 'document existed, continue'
# self.queue.task_done()
continue # get the next document
continue
else:
break
return
def run(self):
while True:
# get the file_path from the Q
if not self.queue.empty():
file_path = self.queue.get()
extension = os.path.splitext(file_path)[-1]
# get the extractor from unique factory
extractor_lock.acquire()
extractor = ExtractorFactory.get_extractor(file_path)
extractor_lock.release()
if extractor is not None and extension in ['.txt']: # only parse the txt file
print 'worker', os.getpid(), 'is parsing', file_path
try:
if extractor.parse_document():
extractor.insert()
else:
print 'parser error for %s, continue' % (file_path,)
except DuplicateKeyError:
print 'document existed, continue'
# self.queue.task_done()
continue # get the next document
continue
else:
break
return
